Gemma 3n E4B Instructed

Leaderboards

Where Gemma 3n E4B Instructed sits among the top 20 in each category.

By task

Scored from votes on each kind of prompt alone, on the same 1,000-point scale.

Test results

Every test Gemma 3n E4B Instructed has a published result on, out of 100%, with its rank among the models that took it.

• GPQA

  #253 / 256

  Graduate-level science questions written to be hard to look up.

  23.7%

  Self-reported

• MMLU-Pro

  #125 / 142

  Broad knowledge and reasoning across 14 subjects, ten answer choices each.

  50.6%

  Self-reported

• AIME 2025

  #120 / 123

  Competition maths problems from the 2025 American Invitational Mathematics Exam.

  11.6%

  Self-reported

• MMLU

  #95 / 103

  Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains

  64.9%

  Self-reported

• LiveCodeBench

  #71 / 76

  LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff.

  13.2%

  Self-reported

• HumanEval

  #49 / 66

  A benchmark that measures functional correctness for synthesizing programs from docstrings, consisting of 164 original programming problems assessing language comprehension, algorithms, and simple mathematics

  75.0%

  Self-reported

• MBPP

  #26 / 33

  MBPP (Mostly Basic Python Problems) is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers. Each problem consists of a task description, code solution, and 3 automated test cases covering programming fundamentals and standard library functionality.

  0.6%

  Self-reported

• MMLU-ProX

  #29 / 32

  Extended version of MMLU-Pro providing additional challenging multiple-choice questions for evaluating language models across diverse academic and professional domains. Built on the foundation of the Massive Multitask Language Understanding benchmark framework.

  19.9%

  Self-reported

• Include

  #26 / 31

  Include benchmark - specific documentation not found in official sources

  57.2%

  Self-reported

• MGSM

  #23 / 31

  MGSM (Multilingual Grade School Math) is a benchmark of grade-school math problems. Contains 250 grade-school math problems manually translated from the GSM8K dataset into ten typologically diverse languages: Spanish, French, German, Russian, Chinese, Japanese, Thai, Swahili, Bengali, and Telugu. Evaluates multilingual mathematical reasoning capabilities.

  67.0%

  Self-reported

• WMT24++

  #17 / 24

  WMT24++ is a comprehensive multilingual machine translation benchmark that expands the WMT24 dataset to cover 55 languages and dialects. It includes human-written references and post-edits across four domains (literary, news, social, and speech) to evaluate machine translation systems and large language models across diverse linguistic contexts.

  50.1%

  Self-reported

• Global-MMLU-Lite

  #11 / 16

  A lightweight version of Global MMLU benchmark that evaluates language models across multiple languages while addressing cultural and linguistic biases in multilingual evaluation.

  64.5%

  Self-reported

• HiddenMath

  #8 / 13

  Google DeepMind's internal mathematical reasoning benchmark that introduces novel problems not encountered during model training to evaluate true mathematical reasoning capabilities rather than memorization

  37.7%

  Self-reported

• LiveCodeBench v5

  #6 / 9

  LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff.

  25.7%

  Self-reported

• ECLeKTic

  #1 / 8

  A multilingual closed-book question answering dataset that evaluates cross-lingual knowledge transfer in large language models across 12 languages, using knowledge-seeking questions based on Wikipedia articles that exist only in one language

  19.0%

  Self-reported

• Global-MMLU

  #5 / 8

  A comprehensive multilingual benchmark covering 42 languages that addresses cultural and linguistic biases in evaluation, with improved translation quality and culturally sensitive question subsets.

  60.3%

  Self-reported

• Codegolf v2.2

  #1 / 4

  Codegolf v2.2 benchmark

  16.8%

  Self-reported

• OpenAI MMLU

  #1 / 2

  MMLU (Massive Multitask Language Understanding) is a comprehensive benchmark that measures a text model's multitask accuracy across 57 diverse academic and professional subjects. The test covers elementary mathematics, US history, computer science, law, morality, business ethics, clinical knowledge, and many other domains spanning STEM, humanities, social sciences, and professional fields. To attain high accuracy, models must possess extensive world knowledge and problem-solving ability.

  35.6%

  Unverified